canli-validation-mcp

Minimum track record length

validate_track_record

Calculate the minimum track record length for an observed Sharpe to beat a benchmark at a chosen confidence, and estimate its probabilistic Sharpe from live or paper records.

Instructions

Minimum track record length (observations and years) for an observed Sharpe to beat a benchmark at a confidence level; with observations, the record's probabilistic Sharpe so far. For live or paper records; to size a backtest for its trials, use validate_backtest_length. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

Input Schema

TableJSON Schema

Name	Required	Description
`skew`	Yes	Skewness of returns; 0 if Normal.
`confidence`	No	Between 0 and 1; default 0.95.
`observations`	No	Record length so far, for its probabilistic Sharpe.
`periods_per_year`	Yes	Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly.
`non_excess_kurtosis`	Yes	Kurtosis, not excess kurtosis; 3 if Normal.
`observed_sharpe_annualized`	Yes	Annualized Sharpe as observed.
`benchmark_sharpe_annualized`	No	Annualized Sharpe to beat; default 0.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`note`	No
`error`	No
`limits`	No
`receipt`	No
`computed`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.13.0Oct 7, 2026

removedOutput schema / additionalProperties
```
Removed value: -{}
```
removedOutput schema / properties / data / additionalProperties
```
Removed value: -{}
```

changedOutput schema / properties / error / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / receipt / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed5 schema fields changedv0.10.1Sep 30, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedInput schema / properties / observations / description

Previous value: -"Record length so far, to get its probabilistic Sharpe."New value: +"Record length so far, for its probabilistic Sharpe."

changedInput schema / properties / periods_per_year / description

Previous value: -"Observations per year: 252 daily, 365 daily crypto, 52 weekly, 12 monthly."New value: +"Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly."

changedInput schema / properties / skew / description

Previous value: -"Skewness of the returns; below -0.5 the reading warns that the counts are too generous."New value: +"Skewness of returns; 0 if Normal."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "description": "data.result holds the statistics (data.plain_reading states them); limits say what the result does not establish; receipt ({id, url}) is the signed record, null when none was stored; error ({code, message}) is set only on refusal.",
+  "properties": {
+    "computed": {
+      "type": "string"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    },
+    "error": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "limits": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "receipt": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changed7 schema fields changedv0.6.0Sep 26, 2026

addedInput schema / properties / benchmark_sharpe_annualized / description
```
Added value: +"Annualized Sharpe to beat; default 0."
```
addedInput schema / properties / confidence / description
```
Added value: +"Between 0 and 1; default 0.95."
```
addedInput schema / properties / non_excess_kurtosis / description
```
Added value: +"Kurtosis, not excess kurtosis; 3 if Normal."
```

addedInput schema / properties / observations / description

Added value: +"Record length so far, to get its probabilistic Sharpe."

addedInput schema / properties / observed_sharpe_annualized / description
```
Added value: +"Annualized Sharpe as observed."
```

addedInput schema / properties / periods_per_year / description

Added value: +"Observations per year: 252 daily, 365 daily crypto, 52 weekly, 12 monthly."

addedInput schema / properties / skew / description

Added value: +"Skewness of the returns; below -0.5 the reading warns that the counts are too generous."

First observedv0.5.0Sep 25, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true) and the description does not contradict them. Beyond that, it adds a genuine interpretive caveat that the outputs "are not admission to anything and are not a forecast," which is useful behavioral context about how results should be read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded and the alternative tool and interpretive caveat follow. It is dense with semicolons and clauses, but each clause carries distinct information and nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is unnecessary, and all parameters are fully documented in the schema. The description supplies purpose, scope, the sibling alternative, and an interpretation caveat, leaving little an agent would need to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all seven parameters with ranges and defaults. The description adds only the conditional meaning of the observations parameter ("with observations, the record's probabilistic Sharpe so far"), which is a marginal gain over the schema's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (minimum track record length in observations and years) and the computation it performs (Sharpe beating a benchmark at a confidence level), and it distinguishes itself by naming the sibling validate_backtest_length for the backtest-sizing case. The core action is expressed as a noun phrase rather than a verb, which slightly softens the clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the applicable domain ("For live or paper records") and names the alternative with the condition that selects it ("to size a backtest for its trials, use validate_backtest_length"). This is explicit routing, though it stops short of enumerating when-not conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.